Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4632 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1563787 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1602332 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1422450 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1569056 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1522535 (Python Code)

Max Activating Token Index: 694

Text #5

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1371415 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1500725 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1453564 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1535261 (Python Code)

Max Activating Token Index: 252

Text #9

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1470549 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1374436 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1395844 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1444113 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1518493 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1461028 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1546722 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1537381 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1491691 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1444409 (Python Code)

Max Activating Token Index: 426